Background initialization in video data using singular value decomposition and robust principal component analysis

Abstract

AbstractBackground initialization is used in video processing applications to extract a scene without the foreground scene. In recent times, the issue of background initialization has gained researchers’ attention in different fields such as video surveillance, video segmentation, computational photography, and so on. The initialization of the background is affected due to different complex dissimilarities such as shadow, intermittent movement, illumination, camera jitter, and clutter. To overcome the aforementioned issues, this paper proposes a decomposition using the combination of the Singular Value Decomposition (SVD) and Robust Principal Component Analysis (RPCA) for Singular Spectrum Analysis (SSA) to perform an effective background initialization. The incorporation of RPCA in SVD is used to overcome the issues related to non-Gaussian noise and it also uses an effective structural knowledge of the video input i.e. sparse and low rank matrix which improves the Peak-Signal-to-Noise-Ratio (PSNR) of the background image. The SBI dataset was used to analyze the performances of SSA-SVDRPCA. The SSA-SVDRPCA is analyzed using MultiScale Structural Similarity Index (MSSSIM), Average gray-level error (AGE), Percentage of clustered error pixels (pCEPS), Percentage of error pixels (pEPs), and PSNR. The existing approaches such as Background Initialization Singular Spectrum Analysis (BISSA) and Quaternion-based Dynamic Mode Decomposition (Q-DMD) are used to compare with the SSA-SVDRPCA method. The PSNR of the SSA-SVDRPCA for Board class is 30.39 dB which is higher than the BISSA and Q-DMD.KEYWORDS: Background initializationdecompositionpeak-signal-to-noise-ratiorobust principal component analysissingular spectrum analysissingular value decomposition Disclosure statementNo potential conflict of interest was reported by the author(s).Data availability statementThe datasets generated during and/or analyzed during the current study are available in the Scene Background Initialization (SBI) dataset.SBI datasethttps://sbmi2015.na.icar.cnr.it/SBIdataset.htmlAdditional informationNotes on contributorsVishruth B. GowdaVishruth B. Gowda completed his BE in AIEMS, bangalore, karnataka and Mtech from EWIT. He currently works as an assistant professor in Department of ISE,SJB Institute of technology. He is also pursuing his research in VTU, Belagavi, Karnataka under the supervision of Dr. M T Gopalakrishna. His research area falls under the domain of comuter vision and image processing.M. T. GopalakrishnaM. T. Gopalakrishna received B. E degree (Computer Science & Engineering) from M. S Ramaiah Institute of Technology, India, M. Tech degree from Visvesvaraya Technological University, Karnataka, India and PhD from Visvesvaraya Technological University, Karnataka, India. He has more than 22 years of teaching experience. He is currently Professor & Head, Department of Artificial Intelligence and Machine Learning in SJB Institute of Technology, Bangalore, India. He has published more than 63 papers in various International journals, International conferences and National conferences. His current research is Pattern Recognition, Digital Image Processing & Computer Vision.J. MeghaJ. Megha working as assistant professor in department of ARTIFICAL INTELLIGENCE and MACHINE LEARNING, MSRIT. research focuses on pattern recognition and image processing.Shilpa MohankumarShilpa Mohankumar works as an assistant professor in Department of ISE,BIT. Her research interest includes image processing, computer vision and pattern recognition.